From f6d701624c57eda76132d5933b446a5d9252438c Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Mon, 18 Dec 2023 18:05:02 -0800 Subject: [PATCH] UI: mention that QuIP# does not work on Windows --- modules/loaders.py | 1 + modules/ui_model_menu.py | 1 + 2 files changed, 2 insertions(+) diff --git a/modules/loaders.py b/modules/loaders.py index a532830b..45769410 100644 --- a/modules/loaders.py +++ b/modules/loaders.py @@ -155,6 +155,7 @@ loaders_and_params = OrderedDict({ 'trust_remote_code', 'no_use_fast', 'no_flash_attn', + 'quipsharp_info', ], 'HQQ': [ 'hqq_backend', diff --git a/modules/ui_model_menu.py b/modules/ui_model_menu.py index ae50f697..7daead70 100644 --- a/modules/ui_model_menu.py +++ b/modules/ui_model_menu.py @@ -102,6 +102,7 @@ def create_ui(): shared.gradio['alpha_value'] = gr.Slider(label='alpha_value', minimum=1, maximum=8, step=0.05, info='Positional embeddings alpha factor for NTK RoPE scaling. Recommended values (NTKv1): 1.75 for 1.5x context, 2.5 for 2x context. Use either this or compress_pos_emb, not both.', value=shared.args.alpha_value) shared.gradio['rope_freq_base'] = gr.Slider(label='rope_freq_base', minimum=0, maximum=1000000, step=1000, info='If greater than 0, will be used instead of alpha_value. Those two are related by rope_freq_base = 10000 * alpha_value ^ (64 / 63)', value=shared.args.rope_freq_base) shared.gradio['compress_pos_emb'] = gr.Slider(label='compress_pos_emb', minimum=1, maximum=8, step=1, info='Positional embeddings compression factor. Should be set to (context length) / (model\'s original context length). Equal to 1/rope_freq_scale.', value=shared.args.compress_pos_emb) + shared.gradio['quipsharp_info'] = gr.Markdown('QuIP# only works on Linux.') with gr.Column(): shared.gradio['triton'] = gr.Checkbox(label="triton", value=shared.args.triton)